Intelligent environmental control system and method for silkworm breeding

Abstract

The present invention relates to the field of environmental control technology, and more particularly to an intelligent environmental control system and method for silkworm breeding. The method comprises the following steps: real-time monitoring of a silkworm breeding community and classification of the silkworms' growth stages to obtain silkworm growth stage data; analyzing the differences in environmental requirements between different silkworms based on the silkworm growth stage data and evaluating the interaction effects of clustering behavior and environment between different silkworm growth stages to obtain clustering behavior and environment interaction effect data; optimizing the global intelligent control of the silkworm breeding environment based on the clustering behavior and environment interaction effect data to obtain intelligent environmental control optimization data; and designing an automated silkworm breeding environment control management strategy based on the intelligent environmental control optimization data to implement intelligent environmental control for silkworm breeding. The present invention further improves intelligent environmental control technology by optimizing the intelligent environmental control technology.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental control, and in particular to an intelligent environmental control method and system for silkworm breeding. Background Art

[0002] Silkworm rearing is an agricultural activity that demands extremely high environmental conditions. Previous methods relied on natural conditions and were susceptible to seasonal variations and climate fluctuations. To improve the efficiency and stability of silkworm rearing, intelligent environmental control technology has emerged. This method, suitable for silkworm rearing in greenhouses, leverages modern technologies such as sensor networks, the Internet of Things, big data, and artificial intelligence to monitor and control key parameters in the rearing environment, such as temperature, humidity, light, and ventilation, in real time, ensuring optimal conditions for silkworm growth. Specifically, the intelligent environmental control system automatically adjusts environmental parameters to the silkworm's different growth stages, keeping them within optimal ranges. This reduces disease incidence and improves silkworm growth and health. Furthermore, through data analysis and prediction, it provides farmers with scientific management recommendations, optimizes rearing strategies, and maximizes economic benefits. Intelligent environmental control methods not only enhance the automation and refined management capabilities of silkworm rearing, but also significantly reduce the labor intensity and error rates of manual operations, promoting the transformation of traditional agriculture towards modernization and intelligentization. However, a traditional intelligent environmental control method for silkworm breeding has the problem of being unable to accurately regulate the local environmental changes caused by the aggregation behavior of silkworms during the silkworm breeding process, and having poor control effect on the balance of the silkworm breeding environment in the entire region. Summary of the Invention

[0003] Based on this, it is necessary to provide an intelligent environmental control system and method for silkworm breeding to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent environment control method for silkworm breeding is provided, the method comprising the following steps:

[0005] Step S1: acquiring silkworm growth cycle data; performing real-time monitoring on a silkworm breeding community to obtain a set of monitoring images of the silkworm breeding community; classifying the set of monitoring images of the silkworm breeding community according to the silkworm growth cycle data to obtain data on the growth stage of the silkworm;

[0006] Step S2: Analyzing the environmental requirements differences among different silkworms on the data of the silkworms' growth stages to obtain silkworm environmental requirements difference data; identifying silkworm aggregation behavior on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data; and evaluating the aggregation behavior-environment interaction effect among different silkworm growth stages on the silkworm environmental requirements difference data based on the silkworm aggregation behavior data to obtain aggregation behavior-environment interaction effect data;

[0007] Step S3: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; and optimizing the global balance of silkworm rearing environment intelligent control according to the behavior-environment demand regulation data to obtain environmental intelligent control optimization data.

[0008] Step S4: Design an automated silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the silkworm breeding environment control management strategy, and send the silkworm breeding environment control management strategy to the cloud platform to execute the silkworm breeding intelligent environment control.

[0009] This method understands the complete life cycle of silkworms, from hatching to adulthood, and the temporal characteristics of each stage. This data can help farmers and breeders develop precise feeding plans and schedules, thereby maximizing production efficiency and product quality. Real-time monitoring allows for the timely detection and resolution of anomalies in silkworm rearing, such as disease, food supply issues, or environmental changes. This helps reduce losses and improve breeding efficiency. Image collections can quantitatively analyze the number, distribution, and health of silkworms within a colony, providing objective data support for breeding management. This monitoring method is more accurate and reliable than traditional visual inspection. Classifying and processing monitoring images according to the silkworm's growth stage allows precise assessment of the silkworm's condition and needs at each stage. This classification guides feeding plans, disease prevention and treatment, and timely harvesting and processing arrangements. Obtaining detailed growth stage data facilitates analysis and optimization of the breeding process. By comparing data from different growth stages, potential optimization points can be identified, such as improved feed formulations and optimized temperature and humidity control, thereby increasing silkworm growth rate and yield. By analyzing the differences in environmental requirements at different silkworm growth stages, the ideal conditions for temperature, humidity, light, and other environmental factors can be determined for each stage. This helps breeders optimize the rearing environment and provide more suitable growth conditions, thereby promoting healthy growth and high silkworm production. Aggregation behavior data can reveal the aggregation patterns and behavioral characteristics of silkworms at different growth stages. This data not only helps understand how silkworms interact within a group but also provides opportunities for breeders to optimize strategies, such as adjusting stocking density and improving air circulation, to reduce the risk of disease transmission and enhance production efficiency. Evaluating the interaction between aggregation behavior and environmental demands can help understand how environmental factors influence silkworm aggregation behavior and how aggregation behavior in turn affects the environment. This in-depth analysis helps optimize the design and management strategies of aquaculture systems, thereby improving overall breeding efficiency and health. Environmental demand control based on aggregation behavior-environment interaction data allows precise adjustment of the aquaculture environment to meet the environmental and physiological needs of silkworms at each different growth stage during aggregation behavior. This data-driven control approach maximizes silkworm growth, health, and yield while minimizing energy and resource waste. Leveraging behavioral activity-environment demand control data for intelligent environmental control optimization can achieve a global balance in the aquaculture environment. This means taking into account the environmental needs of silkworms in concentrated areas while also ensuring that the needs of those in less concentrated areas are met. Based on data from intelligent environmental control optimization, precise and efficient environmental control and management strategies for silkworm rearing can be designed. Based on real-time monitoring and data analysis, these strategies can tailor temperature, humidity, lighting, and other parameters of the rearing environment to best meet the silkworms' growth needs. Through automated control, farmers can reduce the need for manual intervention, improve management efficiency, and ensure that silkworms grow in optimal environmental conditions.The designed breeding environment control management strategy is sent to the cloud platform for execution to realize the intelligent management of mulberry silkworm breeding. The cloud platform can respond to data in real time and automatically adjust the breeding environment according to the preset strategy to maintain a stable optimized state. This intelligent environmental control not only improves the consistency and predictability of production, but also reduces the errors of human operation, reduces operating costs and energy consumption. Therefore, the present invention is an optimization treatment of a traditional intelligent environmental control method for mulberry silkworm breeding, which solves the problem that a traditional intelligent environmental control method for mulberry silkworm breeding cannot accurately regulate the local regional environmental changes caused by the aggregation behavior of mulberry silkworms during the mulberry silkworm breeding process, and the problem that the balance control effect of the whole regional mulberry silkworm breeding environment is poor, improves the accuracy of the local regional environmental regulation of the local regional environmental changes caused by the aggregation behavior of mulberry silkworms, and improves the ability to balance the whole regional mulberry silkworm breeding environment.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Acquire silkworm growth cycle data;

[0012] Step S12: real-time monitoring of the silkworm breeding colony is performed using electronic monitoring equipment to obtain a set of monitoring images of the silkworm breeding colony;

[0013] Step S13: performing image sharpening processing on the silkworm breeding colony monitoring image set to obtain a silkworm colony monitoring sharpened image set;

[0014] Step S14: classifying the silkworm colony monitoring sharpened image set according to the silkworm growth cycle data to obtain the silkworm growth stage data.

[0015] This invention uses detailed silkworm growth cycle data to enable farmers to accurately understand the developmental process of silkworms from hatching to adulthood, as well as the duration of key growth stages. This data provides a foundation for developing optimized breeding plans, helping ensure optimal management at every stage of the breeding process. Real-time monitoring of silkworm breeding colonies through electronic monitoring equipment allows farmers to promptly detect and address potential health issues or environmental changes, as well as assess the current vital signs of individual silkworms. This timely response capability helps reduce losses and improve production efficiency, ensuring that silkworms grow rapidly under optimal conditions. Image sharpening processing of the monitored image sets enhances image clarity and detail, allowing farmers to more accurately observe and analyze the status and health of the silkworm colony. This processing improves data quality and reliability, facilitating the precise identification of abnormalities within the silkworm population. Classifying the sharpened image sets by growth stage based on the growth cycle data allows farmers to accurately assess the status of silkworms at each stage. This classification facilitates the development of targeted management strategies, including feeding, disease prevention, and harvesting schedules, thereby maximizing production efficiency and product quality.

[0016] Preferably, step S2 includes the following steps:

[0017] Step S21: performing an analysis on the environmental demand differences between different silkworm growth stages based on the silkworm growth cycle data to obtain silkworm environmental demand difference data;

[0018] Step S22: performing stage-by-stage clustering difference quantification on the silkworm environmental demand difference data to obtain environmental demand difference clustering quantification data;

[0019] Step S23: performing silkworm aggregation behavior recognition on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data;

[0020] Step S24: evaluating the aggregation behavior-environment interaction effect between different silkworm growth stages based on the clustering quantification data of environmental demand differences according to the silkworm aggregation behavior data, and obtaining the aggregation behavior-environment interaction effect data.

[0021] By analyzing the differences in environmental requirements at different silkworm growth stages, this method allows breeders to understand the specific requirements of silkworms for factors such as temperature, humidity, and light at each stage. This data helps optimize the breeding environment and provide optimal growth conditions, thereby promoting healthy growth and high silkworm yields. Quantifying the differences in environmental requirements across different stages of silkworm growth can help breeders more systematically understand and manage the changing needs of silkworms at different growth stages. This quantitative analysis provides a basis for customized breeding strategies, enabling breeders to more effectively adjust and optimize the breeding environment. Based on the clustering, it is necessary to quantify the differences in environmental requirements between different stages. This involves measuring and describing the degree of differences between different cluster groups. By quantifying these differences, the degree and pattern of changes in environmental requirements between different stages can be precisely understood. By identifying the aggregation behavior of silkworms, the aggregation patterns and behavioral characteristics of silkworm populations under different time periods and environmental conditions can be understood. This data not only helps assess the adaptability and stability of the breeding environment but also provides breeders with optimization recommendations, such as adjusting stocking density or improving air circulation, to improve production efficiency and health. Assessing the interactive effects between aggregation behavior and differences in environmental demands can reveal how environmental factors influence silkworm group behavior and how group behavior in turn influences the environment. This in-depth analysis can help optimize the design and management strategies of aquaculture systems, thereby improving overall aquaculture efficiency and health.

[0022] Preferably, step S24 includes the following steps:

[0023] Step S241: performing aggregation density calculation on the silkworm aggregation behavior data to obtain silkworm aggregation density data; performing aggregation creep friction frequency calculation on the silkworm aggregation behavior data to obtain silkworm aggregation creep friction frequency data;

[0024] Step S242: performing aggregation temperature effect simulation based on the silkworm aggregation density data and the silkworm aggregation creep friction frequency data to obtain aggregation temperature effect simulation data;

[0025] Step S243: performing aggregation effect temperature increment calculation on the aggregation temperature effect simulation data to obtain aggregation effect temperature increment data;

[0026] Step S244: simulating the stress state of silkworms at different growth stages based on the clustered temperature increment data of the environmental demand difference clustering quantification data to obtain silkworm stress state simulation data;

[0027] Step S245: performing calculation on the silkworm stress state simulation data to determine the difference in silkworm vitality loss between different growth stages, and obtaining silkworm vitality loss difference data;

[0028] Step S246: Based on the aggregation effect temperature increment data, the silkworm stress state simulation data and the silkworm vitality loss difference data, the environmental demand difference clustering quantitative data is evaluated to obtain the aggregation behavior environment interaction effect data between different silkworm growth stages.

[0029] By calculating the cluster density and peristaltic friction frequency of silkworms, this method provides a detailed understanding of the clustering behavior characteristics of silkworm populations. Cluster density data reflects the density of a silkworm population, while peristaltic friction frequency indicates the level of movement activity within the population. These data provide a foundation for subsequent steps, helping to understand how cluster behavior responds to environmental changes. Cluster temperature effect simulations based on cluster density and peristaltic friction frequency data can simulate the thermal effects of silkworm populations at different densities and movement frequencies. This simulation provides information on the distribution and variation of temperature within a silkworm population, helping to optimize temperature control strategies in the breeding environment and ensure that silkworms grow within a suitable temperature range. Calculating the cluster effect temperature increment based on the cluster temperature effect simulation data can quantify the extent of the silkworm population's impact on the ambient temperature. This data provides a basis for understanding and predicting the stress response of silkworms under different clustering conditions, helping to adjust the breeding environment to reduce stress and improve production efficiency. Simulating silkworm stress based on the cluster effect temperature increment data can simulate the stress response of silkworms at different growth stages. These simulation data provide in-depth insights into the physiological and behavioral changes of silkworms under different clustering environments, supporting the development of personalized management strategies. Calculating differences in vigor loss at different silkworm growth stages quantifies the potential impact of aggregation behavior on silkworm growth and health. This data helps farmers better understand how aggregation behavior affects silkworm growth efficiency and yield, thereby optimizing the breeding environment and management practices. By comprehensively considering aggregation-effect temperature increments, simulated silkworm stress states, and vigor loss difference data, the interactive effects between aggregation behavior and differences in environmental requirements are evaluated. This assessment provides a deeper understanding of how silkworm group behavior affects the breeding environment, providing a scientific basis and data support for optimizing breeding systems.

[0030] Preferably, calculating the variance of vitality loss between different silkworm growth stages for silkworm stress state simulation data comprises the following steps:

[0031] The slowness of silkworm peristalsis frequency between different silkworm growth stages is evaluated based on the simulated data of silkworm stress state, and the slowness of silkworm peristalsis frequency data is obtained;

[0032] The slowdown fluctuation interval of silkworm peristalsis frequency at different growth stages was calculated based on the slowdown data of silkworm peristalsis frequency, and the slowdown fluctuation interval of silkworm peristalsis frequency was obtained.

[0033] According to the slow fluctuation interval of peristalsis frequency, the slow fluctuation logarithm transformation is performed on the peristalsis frequency data of silkworms to obtain the slow fluctuation logarithm transformation data;

[0034] The skewness of the slowing time series distribution is analyzed on the logarithmic transformation data of slowing fluctuations to obtain the skewness of the slowing time series distribution data;

[0035] According to the skewness data of the slowing time series distribution, the slowing numerical value approximate interval is calculated for the slowing fluctuation logarithm transformation data, and the slowing numerical value approximate interval is obtained;

[0036] Based on the grey correlation method and the approximate interval of the slowing value, the nonlinear slowing constraint analysis of the peristaltic frequency slowing fluctuation interval was carried out to obtain the peristaltic frequency slowing correlation data.

[0037] The difference in silkworm vitality loss between different growth stages was calculated based on the correlation data of peristalsis frequency slowing down, and the difference in silkworm vitality loss data was obtained.

[0038] The present invention evaluates the slowing down of the peristaltic frequency of silkworms under the internal stress state at different growth stages, that is, the trend of frequency change over time. The changing characteristics of the peristaltic frequency of silkworms in different growth stages are understood to provide basic data for subsequent steps. Based on the peristaltic frequency slowing down data, the fluctuation range of the peristaltic frequency of silkworms in different growth stages is calculated. The fluctuation range of the peristaltic frequency of silkworms in different growth stages is determined to reveal the amplitude and trend of the peristaltic frequency change of silkworms in different growth stages, providing a data basis for subsequent analysis. The peristaltic frequency slowing down fluctuation range data is used to perform logarithmic transformation to make the data more linear and suitable for further statistical analysis, reduce the volatility of the data, more accurately reflect the peristaltic frequency change trend between different growth stages, and provide a more stable and reliable data basis for subsequent analysis. The time series distribution skewness of the slowing down fluctuation logarithmic transformation data is analyzed, that is, the distribution characteristics of the data in the time series. Understanding the distribution characteristics and skewness of the data in different growth stages helps to understand the unevenness and biological explanation of the frequency change. Based on the slowing down time series distribution skewness data, the numerical approximate interval of the slowing down fluctuation logarithmic transformation data is calculated. A more specific numerical range is provided to reflect the specific magnitude and direction of changes in silkworm peristalsis frequency at different growth stages. The degree of vitality loss in silkworms at different growth stages is calculated using the grey correlation method and the approximate interval of the trend-slowing value. The differences in vitality loss under stress at different growth stages are quantified, revealing the potential impact of frequency changes on silkworm growth and health.

[0039] Preferably, step S3 includes the following steps:

[0040] Step S31: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; wherein the behavior-environment demand regulation data includes behavior-environment temperature regulation data and behavior-environment airflow regulation data;

[0041] Step S32: Calculating the impact of the silkworm breeding gathering behavior on the adjacent activity area based on the behavior activity environment demand control data to obtain the adjacent activity area environmental impact data;

[0042] Step S33: identifying the degree of azimuth distribution environmental impact of the silkworm breeding aggregation behavior in the vicinity of the activity area based on the environmental impact data of the vicinity of the activity area, and obtaining the azimuth distribution environmental impact degree data;

[0043] Step S34: performing intelligent control optimization of the global balance of the environment for silkworm breeding based on the azimuth distribution environmental impact degree data and the behavioral activity environmental demand regulation data to obtain environmental intelligent control optimization data.

[0044] The present invention adjusts the temperature and airflow in the breeding environment according to the aggregation behavior characteristics of the silkworm group, ensuring that the silkworms grow and reproduce under suitable environmental conditions, thereby improving production efficiency and quality. Understanding the impact of the aggregation behavior of silkworms on the surrounding environment, including the diffusion and regulatory effects of temperature and airflow, helps to optimize the breeding space layout and management strategies to meet the growth needs of silkworms to the greatest extent. Determining the differences in environmental impacts in different directions helps optimize the spatial layout and regulatory strategies to provide a balanced growth environment and ensure that the silkworms remain healthy and energetic throughout the breeding process. Through an intelligent control system, dynamic adjustment of the breeding environment is achieved, maintaining the stability and balance of environmental parameters within an ideal range, and improving the growth efficiency and production results of silkworms.

[0045] Preferably, step S31 includes the following steps:

[0046] Step S311: analyzing abnormal temperature fluctuations in aggregation behavior during silkworm rearing based on the aggregation behavior-environment interaction effect data to obtain abnormal temperature fluctuation data in aggregation behavior;

[0047] Step S312: evaluating the temperature fluctuation tolerance of silkworms at different growth stages based on the abnormal temperature fluctuation data of the aggregation behavior and the difference data of the silkworms' environmental requirements, to obtain the temperature fluctuation tolerance data of the silkworms;

[0048] Step S313: simulating the air circulation of the aggregation behavior during the silkworm breeding process according to the aggregation behavior-environment interaction effect data to obtain aggregation behavior air circulation data;

[0049] Step S314: analyzing the air duct barrier effect of the clustering behavior during the silkworm breeding process on the clustering behavior air circulation data to obtain the clustering behavior air duct barrier effect data;

[0050] Step S315: performing demand difference data pairing on the silkworm environmental demand difference data according to the silkworm temperature fluctuation tolerance data and the gathering behavior air duct barrier effect data to obtain environmental demand difference paired data;

[0051] Step S316: performing behavior activity environment demand regulation based on the paired data according to the environmental demand difference, and obtaining behavior activity environment demand regulation data; wherein the behavior activity environment demand regulation data includes behavior activity temperature regulation data and behavior activity airflow regulation data.

[0052] The present invention analyzes abnormal temperature fluctuations caused by the aggregation behavior of silkworms during the breeding process based on the aggregation behavior-environment interaction effect data. By identifying and analyzing abnormal temperature fluctuations, the degree of influence of the aggregation behavior on temperature stability can be revealed, and basic data and reference can be provided for subsequent temperature regulation to ensure that the silkworms grow and reproduce in a stable temperature environment. Based on the abnormal temperature fluctuation data of the aggregation behavior, the tolerance of silkworms at different growth stages to temperature fluctuations is evaluated, and the sensitivity of silkworms at different growth stages to temperature changes is determined, which helps to formulate targeted temperature control strategies and improve the breeding success rate and production efficiency. The aggregation behavior-environment interaction effect data is used to simulate the influence of the aggregation behavior of silkworms on air circulation, understand the influence of the aggregation behavior on air flow in the breeding environment, help evaluate the air quality and oxygen supply, optimize the ventilation design and management of the breeding space, analyze the influence of the aggregation behavior on the air duct barrier effect, that is, how the aggregation behavior affects the ventilation effect of the air duct, identify and evaluate the air duct barrier effect caused by the aggregation behavior, so as to adjust the air duct design and layout to ensure air circulation and the stability of the breeding environment. Based on data on silkworms' tolerance to temperature fluctuations and the air duct barrier effects of their clustering behaviors, we match data on environmental differences and regulate their environmental needs. This data matching and regulation enables precise control of temperature and airflow to create the most suitable breeding environment. This precise regulation improves silkworm growth and quality, reduces losses, and optimizes breeding efficiency.

[0053] Preferably, step S34 includes the following steps:

[0054] Step S341: performing an environmental impact time lag effect analysis on the adjacent activity areas of the silkworm breeding aggregation behavior based on the azimuth distribution environmental impact degree data to obtain distribution environmental impact time lag effect data;

[0055] Step S342: extracting the environmental temperature mutation and analyzing the airflow structure of the area adjacent to the silkworm breeding gathering behavior based on the temperature control data of the behavior activity, the airflow control data of the behavior activity, and the time lag effect data of the distribution environment, to obtain the azimuthally distributed environmental temperature mutation data and the azimuthally distributed airflow structure data;

[0056] Step S343: identifying the spatial distribution mutation and progressive law of the adjacent activity areas of the silkworm breeding and aggregation behavior based on the azimuth distribution environmental temperature mutation data to obtain temperature distribution mutation and progressive law data;

[0057] Step S344: performing intelligent control optimization of the global temperature balance of silkworm rearing based on the temperature distribution mutation and progressive law data and the behavior and activity environment demand control data to obtain temperature balance intelligent control optimization data;

[0058] Step S345: performing an airflow stacking effect analysis on the azimuthally distributed airflow flow structure data for the adjacent activity areas of the silkworm breeding aggregation behavior to obtain azimuthally distributed airflow stacking effect data;

[0059] Step S346: performing intelligent control optimization of the global balance of airflow for silkworm breeding based on the azimuth distribution airflow stacking effect data and the behavioral activity environment demand control data to obtain airflow balance intelligent control optimization data;

[0060] Step S347: performing global balance intelligent control optimization of the silkworm breeding environment according to the temperature balance intelligent control optimization data and the airflow balance intelligent control optimization data to obtain environmental intelligent control optimization data.

[0061] Based on data on the degree of environmental impact of location-based distribution, this invention analyzes the time-lag effect of environmental regulation implemented by mulberry silkworm feeding clustering behavior on the environment of adjacent activity areas. This reveals the time-lag effect of environmental regulation implemented by clustering behavior on the surrounding environment, helping to predict and adjust the impact of environmental changes on silkworm growth and optimize dynamic temperature and airflow control strategies. Based on behavioral temperature control data, behavioral airflow control data, and distributed environmental impact time-lag effect data, this invention analyzes the impact of environmental regulation implemented by mulberry silkworm feeding clustering behavior on the temperature mutation and airflow structure of the adjacent activity areas. This accurately extracts the temperature mutation and airflow structure of the environment, revealing how environmental regulation implemented by clustering behavior affects the temperature and airflow of the adjacent activity areas, providing detailed data support for further optimizing environmental control strategies. By analyzing location-based environmental temperature mutation data, this invention identifies the progressive pattern of temperature changes in the adjacent activity areas caused by mulberry silkworm feeding clustering behavior. By understanding the progressive pattern of temperature distribution, temperature control strategies are optimized to ensure temperature balance and stability during the mulberry silkworm feeding process, thereby improving feeding efficiency and quality. Based on the progressive pattern of temperature distribution mutation and the environmental demand regulation data of the behavioral activities, intelligent control optimization of the global temperature balance in mulberry silkworm feeding is performed. Intelligent control technology is used to dynamically adjust and balance the overall temperature of the breeding environment, ensuring it fluctuates within a suitable range and improving silkworm growth and production efficiency. Analyzing azimuthally distributed airflow structure data evaluates the impact of environmental regulation during silkworm breeding clusters on the stacking effect of airflow in adjacent activity areas. Understanding how the stacking effect affects air quality and oxygen supply in the breeding environment provides a basis for optimizing ventilation design and management, ensuring air flow and cleanliness within the breeding space. Using intelligent control systems, the distribution and flow structure of airflow are optimized to ensure gas balance and stability within the breeding environment, thereby enhancing silkworm health and production efficiency. Combining intelligent temperature and airflow optimization data, intelligent control optimization of the global balance of the mulberry silkworm breeding environment is achieved. By comprehensively controlling temperature and airflow, a stable and balanced overall environment is achieved, improving silkworm growth quality and economic benefits, and providing scientific and technological support and guarantees for the sustainable development of the breeding industry.

[0062] Preferably, performing intelligent control optimization of airflow global balance on behavioral activity environment demand regulation data based on azimuth distribution airflow stacking effect data includes the following steps:

[0063] The airflow backflow path simulation of the adjacent activity area of ​​mulberry silkworm feeding aggregation behavior was carried out on the azimuthally distributed airflow stacking effect data to obtain the airflow backflow path simulation data;

[0064] The difficulty of airflow exchange and diffusion is evaluated based on the azimuthal distribution airflow stacking effect data based on the airflow return path simulation data to obtain the airflow exchange and diffusion difficulty data;

[0065] Optimize the airflow direction angle control based on the airflow exchange and diffusion difficulty data to obtain airflow direction angle control data;

[0066] Performing airflow velocity control adaptation on the airflow exchange and diffusion difficulty data according to the airflow direction angle control data to obtain airflow velocity control adaptation data;

[0067] Based on the airflow direction angle control data, airflow velocity control adaptation data and behavioral activity environment demand regulation data, the global airflow balance intelligent control optimization of silkworm breeding is carried out to obtain the airflow balance intelligent control optimization data.

[0068] Based on data on the azimuthally distributed airflow stacking effect, the present invention simulates the airflow return paths within adjacent activity areas of mulberry silkworm rearing clusters. By simulating the airflow return paths, we understand the trajectory of airflow within the rearing environment, helping to optimize airflow fluidity and uniformity, ensuring effective ventilation and gas exchange across the entire environment. Based on the simulated airflow return path data, we assess the exchange and diffusion difficulty of the azimuthally distributed airflow stacking effect. Understanding the exchange difficulty of airflow within different areas helps identify bottlenecks and obstacles to airflow, providing a basis for subsequent flow direction control and flow rate regulation. Based on the airflow exchange and diffusion difficulty data, we optimize the airflow direction angle. By optimizing the airflow direction angle, we ensure efficient airflow within the rearing environment, avoid dead spots and air obstructions, and improve overall ventilation and air quality. Based on the airflow direction angle control data, we adapt the airflow velocity control strategy. Adjusting the airflow velocity according to actual needs ensures balanced and stable airflow within each area, effectively avoiding environmental unevenness caused by excessively fast or slow airflow. By combining the airflow direction angle control data, airflow velocity control adaptation data, and behavioral activity environment demand regulation data, we perform intelligent control optimization of the global airflow balance in mulberry silkworm rearing. By comprehensively controlling the direction and speed of the airflow, the gas balance and fluidity in the breeding environment can be achieved, the comfort and growth efficiency of the silkworms can be improved, thereby increasing the breeding output and quality.

[0069] Preferably, the present invention further provides an intelligent environmental control system for silkworm breeding, which is used to execute the intelligent environmental control method for silkworm breeding as described above. The intelligent environmental control system for silkworm breeding comprises:

[0070] The silkworm growth stage classification module is used to obtain the silkworm growth cycle data; perform real-time monitoring of the silkworm breeding community to obtain a set of silkworm breeding community monitoring images; classify the silkworm breeding community monitoring image set according to the silkworm growth cycle data to obtain the silkworm growth stage data;

[0071] The silkworm aggregation behavior environment analysis module is used to analyze the environmental demand differences between different silkworms based on the data of silkworm growth stages, and obtain the silkworm environmental demand difference data; identify the silkworm aggregation behavior based on the silkworm breeding community monitoring image set, and obtain the silkworm aggregation behavior data; and evaluate the aggregation behavior environment interaction effect between different silkworm growth stages based on the silkworm environmental demand difference data, and obtain the aggregation behavior environment interaction effect data;

[0072] The global control optimization module for silkworm rearing is used to regulate the environmental demand of silkworms' behavior activities based on the aggregated behavior-environment interaction effect data, and obtain the behavior-environment demand regulation data; and to optimize the global balance of the silkworm rearing environment intelligent control based on the behavior-environment demand regulation data, and obtain the environmental intelligent control optimization data;

[0073] The control management strategy execution module is used to design an automated mulberry silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the mulberry silkworm breeding environment control management strategy, and send the mulberry silkworm breeding environment control management strategy to the cloud platform to execute the mulberry silkworm breeding intelligent environment control.

[0074] Therefore, the present invention is an optimization treatment of a traditional intelligent environmental control method for mulberry silkworm breeding, which solves the problems of the traditional intelligent environmental control method for mulberry silkworm breeding, that is, the inability to accurately regulate the local regional environment due to the local regional environmental changes caused by the aggregation behavior of silkworms during the silkworm breeding process, and the poor effect of controlling the balance of the mulberry silkworm breeding environment in the entire region. It improves the accuracy of local regional environmental regulation due to the local regional environmental changes caused by the aggregation behavior of silkworms, and enhances the ability to control the balance of the mulberry silkworm breeding environment in the entire region. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A schematic flow chart of the steps of an intelligent environment control method for silkworm breeding;

[0076] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0077] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0078] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0079] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative work are within the scope of protection of the present invention.

[0080] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0081] To achieve this, please refer to Figures 1 to 3 , an intelligent environment control method for silkworm breeding, the method comprising the following steps:

[0082] Step S1: acquiring silkworm growth cycle data; performing real-time monitoring on a silkworm breeding community to obtain a set of monitoring images of the silkworm breeding community; classifying the set of monitoring images of the silkworm breeding community according to the silkworm growth cycle data to obtain data on the growth stage of the silkworm;

[0083] Step S2: Analyzing the environmental requirements differences among different silkworms on the data of the silkworms' growth stages to obtain silkworm environmental requirements difference data; identifying silkworm aggregation behavior on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data; and evaluating the aggregation behavior-environment interaction effect among different silkworm growth stages on the silkworm environmental requirements difference data based on the silkworm aggregation behavior data to obtain aggregation behavior-environment interaction effect data;

[0084] Step S3: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; and optimizing the global balance of silkworm rearing environment intelligent control according to the behavior-environment demand regulation data to obtain environmental intelligent control optimization data.

[0085] Step S4: Design an automated silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the silkworm breeding environment control management strategy, and send the silkworm breeding environment control management strategy to the cloud platform to execute the silkworm breeding intelligent environment control.

[0086] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of an intelligent environment control method for silkworm breeding according to the present invention. In this example, the intelligent environment control method for silkworm breeding includes the following steps:

[0087] Step S1: acquiring silkworm growth cycle data; performing real-time monitoring on a silkworm breeding community to obtain a set of monitoring images of the silkworm breeding community; classifying the set of monitoring images of the silkworm breeding community according to the silkworm growth cycle data to obtain data on the growth stage of the silkworm;

[0088] In this embodiment of the present invention, key data for each growth stage is first collected by observing and recording the growth of silkworms from egg to adult. This data includes the length of the incubation, larval, pupal, and adult stages, temperature and humidity requirements, feed requirements, and mulberry leaf consumption. This data can be compiled and analyzed through laboratory observations, historical literature review, and data provided by agricultural research institutions. To ensure the accuracy and comprehensiveness of the data, high-precision sensors and recording equipment are used to continuously monitor the silkworms' growth environment and record detailed data for each stage. During the silkworm rearing process, high-resolution cameras and image acquisition systems are used to monitor the rearing colony 24 hours a day. These devices should be installed in various locations in the rearing room to ensure comprehensive coverage of the entire rearing area and capture images of the silkworms from different angles. The image acquisition system should be equipped with an automatic capture function to capture high-definition images of the silkworm colony at regular intervals or as needed. These images will be stored in a database as a monitoring image set for subsequent image processing and analysis. Machine learning and image processing techniques are used to analyze each frame of the silkworm monitoring image set. First, image preprocessing techniques, such as image enhancement and denoising, are used to improve image quality and recognizability. Then, a pre-trained deep learning model is used to identify and classify the silkworms in the images. The model needs to be able to recognize the appearance characteristics of silkworms at different growth stages and classify them into corresponding growth stages based on the silkworm growth cycle data. To ensure classification accuracy, the model's training dataset should contain a large number of images of silkworms at different growth stages, which must be accurately labeled and verified. After the classification process is complete, the silkworm growth stage data corresponding to each image is recorded in a database for subsequent environmental control and management.

[0089] Step S2: Analyzing the environmental requirements differences among different silkworms on the data of the silkworms' growth stages to obtain silkworm environmental requirements difference data; identifying silkworm aggregation behavior on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data; and evaluating the aggregation behavior-environment interaction effect among different silkworm growth stages on the silkworm environmental requirements difference data based on the silkworm aggregation behavior data to obtain aggregation behavior-environment interaction effect data;

[0090] In this embodiment of the present invention, based on the silkworm growth stage data obtained in step S1, the environmental requirements of silkworms at different stages are first summarized and analyzed. These requirements include temperature, humidity, light, ventilation, and feed type and quantity. By comparing the requirements of different growth stages, differences in environmental requirements can be identified. Using statistical analysis software such as SPSS or R, these data are then subjected to statistical methods such as variance analysis and cluster analysis to quantify the differences in environmental requirements among different silkworms. The analysis results generate data on the difference in silkworm environmental requirements, which serves as basic data for the environmental control system, ensuring that silkworms at each growth stage grow in the most suitable environment. Computer vision technology and behavior recognition algorithms are used to analyze the clustering behavior of silkworms in the monitoring image set. First, image segmentation and object detection techniques are used to identify each silkworm in the image. Then, based on the silkworms' locations and movement trajectories, their clustering behavior is analyzed, such as the density, duration, and frequency of clustering within a given area. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) are used to identify and classify the clustering behavior of silkworms. These models require training and validation with a large amount of labeled data to ensure the accuracy and robustness of the recognition results. Aggregation behavior data will be recorded in a database to provide foundational data for subsequent analysis of environmental demand differences and assessment of behavior-environment interaction effects. Using the silkworm aggregation behavior data obtained in step S2 and the environmental demand difference data from step S1, the interaction between aggregation behavior and environmental demand across different silkworm growth stages is assessed. Statistical methods such as multiple regression analysis and factor analysis are used to evaluate the aggregation behavior characteristics of silkworms at different growth stages under varying environmental conditions, as well as the impact of these behaviors on environmental demand, focusing on the impact of aggregation behavior at different growth stages on environmental demand. Local environmental changes, such as temperature, humidity, and gas concentration, under which silkworms at different growth stages aggregate, are analyzed. Then, combined with the environmental demand difference data, the adaptability of silkworms at different growth stages to these environmental changes and their impact on these changes are assessed. Multiple regression analysis and cluster analysis are used to quantify the aggregation behavior and environmental demand of silkworms, revealing the specific manifestations of the aggregation behavior-environment interaction effect across different growth stages. For example, changes in the aggregation density of silkworms in the instar growth stage will cause the local temperature to rise by 2°C, and this temperature change will cause the silkworms in the instar growth stage to feel uncomfortable with the environmental changes. Through this analysis, we can obtain the quantitative relationship between the aggregation behavior of silkworms in different growth stages and their environmental needs, that is, the aggregation behavior-environment interaction effect data, which will cause changes in the local environment of the larval silkworms (such as temperature and air circulation), and the impact of these environmental changes caused by aggregation behavior on their growth rate and health status.By quantifying these interactions, more precise and scientific environmental control strategies can be developed to ensure that silkworms at each stage of growth are optimally positioned to avoid local environmental changes caused by clustering effects. Ultimately, data on clustering behavior and environmental interactions will be recorded in a system database, providing data support for intelligent environmental control.

[0091] Step S3: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; and optimizing the global balance of silkworm rearing environment intelligent control according to the behavior-environment demand regulation data to obtain environmental intelligent control optimization data.

[0092] In the embodiments of the present invention, when regulating the environmental needs of silkworms' behavioral activities based on aggregated behavioral-environment interaction effect data based on differential environmental needs, it is indeed necessary to comprehensively consider the environmental needs of silkworms at all stages of their growth. In addition to considering silkworms of different ages (e.g., ages 1 to 5), other key growth stages, such as moths, eggs, and pupae, should also be considered. In specific implementations, more complex machine learning models, such as deep neural networks (DNNs) or long short-term memory networks (LSTMs), can be used to handle this complex multi-stage, multi-factor relationship. First, environmental requirement data for each stage of the silkworm's life cycle is collected and organized, including but not limited to: Egg stage: optimum temperature 18-25°C, relative humidity 75-80%. Silkworms ages 1 to 5: optimum temperature and humidity ranges for each age stage. Temperature requirements vary before and after clustering. Pupa stage: optimum temperature 25-27°C, relative humidity 70-75%. Moth stage: optimum temperature 23-25°C, relative humidity 70-75%. This data is then combined with the previously obtained aggregated behavioral-environment interaction effect data and input into the machine learning model. The model's input parameters include the current growth stage, the intensity of agglomeration behavior, current environmental parameters (such as temperature, humidity, and light), and historical environmental data. The model outputs the adjusted optimal environmental parameters. For example, the model may discover that during the transition from second- to third-instar silkworms, agglomeration becomes more pronounced due to molting stress. At this time, the temperature should be slightly lowered by 0.5°C to offset the local temperature increase caused by agglomeration. In the late fourth-instar silkworms, their food intake increases and their metabolism is high, making agglomeration more impactful on the local temperature. Therefore, the temperature should be lowered by 1-1.5°C. In the early pupal stage, the silkworms are more sensitive to environmental changes because their bodies have not yet fully hardened. Even if agglomeration occurs, the temperature and humidity should be maintained relatively stable, with only minor adjustments. After model training is complete, real-time data on the silkworm's growth stage and agglomeration behavior can be continuously input to generate dynamically adjusted environmental demand parameters. These parameters are continuously updated as the silkworms' growth stage and agglomeration behavior change, forming a dynamic dataset for regulating environmental demand for behavioral activities. Furthermore, reinforcement learning algorithms, such as the Deep Q-Network (DQN), can be introduced to enable the system to continuously optimize its control strategy through continuous environmental control and feedback. For example, the system can evaluate the effectiveness of environmental control based on indicators such as the silkworm's growth status and silk production, and adjust future control strategies accordingly. This comprehensive, dynamic, and intelligent control approach ensures the optimal growth environment at every stage of the silkworm's life cycle, thereby improving the silkworm's growth quality and silk production.

[0093] Step S4: Design an automated silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the silkworm breeding environment control management strategy, and send the silkworm breeding environment control management strategy to the cloud platform to execute the silkworm breeding intelligent environment control.

[0094] In this embodiment of the present invention, intelligent environmental control optimization data (particularly temperature and airflow data taking into account the clustering effect of silkworms) is imported into a management strategy design platform. The platform uses data analysis tools to conduct a detailed analysis of this optimization data, identifying the impact of silkworm clustering behavior on temperature and airflow. For example, when silkworms cluster, local temperatures rise and airflow decreases, changes that affect silkworm growth. Based on these analysis results, the platform utilizes optimization algorithms (such as linear regression, decision trees, and genetic algorithms) to design an optimal environmental control management strategy. Specific strategies include setting appropriate temperature ranges based on the clustering behavior of silkworms at different growth stages. For example, silkworms require higher temperatures during the incubation period, and local temperatures should not exceed 28°C during clustering. For example, second-instar silkworms have different temperature requirements during clustering. Therefore, the system sets a temperature regulator to maintain a temperature between 26-28°C in the clustering area. Ventilation frequency in the clustering area is increased to ensure smooth airflow and prevent local overheating. The system is configured to automatically activate ventilation equipment when silkworms gather. It also adjusts air speed and direction based on real-time monitoring data to ensure even airflow distribution. The management strategy design platform transmits the generated silkworm rearing environment control strategies to a cloud platform via the network. The cloud platform, acting as the central control center, receives and stores these strategies and, through the Internet of Things (IoT) technology, sends control instructions to various environmental control devices. The cloud platform communicates in real time with sensors and control devices in the rearing environment, such as temperature and humidity regulators and airflow control systems, to ensure that each device operates in accordance with the management strategies. For example, upon receiving the strategy, the cloud platform instructs the temperature regulator to set the temperature in the silkworm gathering area to 26-28°C and controls the airflow system to activate when silkworms gather, increasing ventilation frequency and speed to ensure smooth airflow. The cloud platform also provides remote monitoring and management capabilities, allowing farmers to view temperature and airflow status in real time using mobile devices (such as smartphones and tablets) and adjust control strategies at any time. For example, if farmers detect an abnormally high temperature in the silkworm gathering area through the cloud platform, they can immediately remotely lower the temperature setting and increase the operating time of the ventilation equipment to ensure a suitable growth environment for the silkworms. The cloud platform regularly collects and analyzes environmental data, generating environmental control and performance evaluation reports to help breeders optimize management strategies. These reports include trends in temperature and airflow parameters, equipment operating efficiency, and silkworm growth status, providing comprehensive data support to help breeders make informed decisions.

[0095] Preferably, step S1 includes the following steps:

[0096] Step S11: Acquire silkworm growth cycle data;

[0097] Step S12: real-time monitoring of the silkworm breeding colony is performed using electronic monitoring equipment to obtain a set of monitoring images of the silkworm breeding colony;

[0098] Step S13: performing image sharpening processing on the silkworm breeding colony monitoring image set to obtain a silkworm colony monitoring sharpened image set;

[0099] Step S14: classifying the silkworm colony monitoring sharpened image set according to the silkworm growth cycle data to obtain the silkworm growth stage data.

[0100] In the embodiments of the present invention, data on the specific environmental conditions required by silkworms at various stages of growth (e.g., egg, larva, pupa, and adult) was collected through experiments and literature research. This data includes temperature, humidity, light intensity, and feed requirements. This data was entered into a database, and a timeline of the silkworm's growth cycle was established, noting the start and end times of each stage. For example, the larval stage typically lasts 20-25 days and requires high humidity and moderate temperature. This data allows for an accurate understanding of the specific requirements of silkworms at different stages of growth. High-resolution cameras and other electronic monitoring equipment were installed in the silkworm rearing room for 24-hour, real-time monitoring. Cameras were mounted at various angles on the rearing racks to ensure comprehensive coverage of the entire rearing area and capture clear images. The monitoring equipment transmitted the image data to a central control system via a network, generating a collection of images monitoring the silkworm rearing community. These images record the silkworms' activities and environmental conditions at different time points, providing a wealth of data for subsequent analysis. The acquired collection of images monitoring the silkworm rearing community was then imported into image processing software such as OpenCV and MATLAB. Image sharpening algorithms are used to process images, enhancing edges and details, and improving image clarity and contrast. The specific steps include: first, image preprocessing, such as denoising and grayscale adjustment; then, applying sharpening algorithms such as Laplace sharpening or Unsharp Masking; and finally, image post-processing, adjusting brightness and contrast, to produce a set of sharpened images for silkworm colony monitoring. Image sharpening allows for clearer identification of silkworm morphological characteristics and activity, ensuring the accuracy of subsequent analysis. The silkworm growth cycle data and the set of sharpened images for silkworm colony monitoring are imported into the image processing and analysis platform. The silkworm growth cycle data contains characteristic descriptions of silkworms at different stages. For example, the egg stage: images show small, immobile eggs with a lighter color. The larval stage: images show active larvae with gradually enlarged bodies and darker colors. The pupal stage: images show immobile pupae with a fixed morphology and further darkening colors. The adult stage: images show winged adults capable of flight. This growth cycle data is then used to train an image classification model, such as a convolutional neural network (CNN). During the training process, a large amount of labeled image data is provided, enabling the model to learn and identify the characteristics of silkworms at different growth stages. After training is complete, the sharpened monitoring image set is input into the classification model for classification processing. This allows the silkworm's growth stage to be determined. For example, by identifying the silkworm's body length, color, and activity frequency, it can be determined whether it is in the larval or pupal stage. After classification, the growth stage data for each time point and each silkworm is recorded to generate a data set of silkworm growth stages. This data can be used to track the silkworm's growth progress in real time, providing a scientific basis for environmental control and feeding management.

[0101] Preferably, step S2 includes the following steps:

[0102] Step S21: performing an analysis on the environmental demand differences between different silkworm growth stages based on the silkworm growth cycle data to obtain silkworm environmental demand difference data;

[0103] Step S22: performing stage-by-stage clustering difference quantification on the silkworm environmental demand difference data to obtain environmental demand difference cluster quantification data;

[0104] Step S23: performing silkworm aggregation behavior recognition on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data;

[0105] Step S24: evaluating the aggregation behavior-environment interaction effect between different silkworm growth stages based on the clustering quantification data of environmental demand differences according to the silkworm aggregation behavior data, and obtaining the aggregation behavior-environment interaction effect data.

[0106] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0107] Step S21: performing an analysis on the environmental demand differences between different silkworm growth stages based on the silkworm growth cycle data to obtain silkworm environmental demand difference data;

[0108] In an embodiment of the present invention, the silkworm's growth stages are first divided into the egg stage, the larval stage (1-5 instars), and the pupal stage based on the silkworm's growth cycle data. Silkworms are reared in greenhouses, with different areas within the greenhouse designated for rearing silkworms at different growth stages. For example, an egg-hatching area, a larval-rearing area, a pupal-cocooning room, and an adult-mating area can be established. Environmental monitoring equipment is then used to collect data on environmental parameters such as temperature, humidity, and light intensity at each growth stage in the different rearing areas. Next, statistical analysis software (such as SPSS or R) is used to perform variance analysis and multiple comparisons on the environmental parameters at different growth stages. For example, it can be found that the first-instar larvae require a temperature of 25-28°C and a relative humidity of 80-85%, while the fifth-instar larvae require a temperature of 22-24°C and a relative humidity of 70-75%. This analysis provides specific data on the differences in environmental requirements between each growth stage, providing a basis for subsequent environmental control.

[0109] Step S22: performing stage-by-stage clustering difference quantification on the silkworm environmental demand difference data to obtain environmental demand difference clustering quantification data;

[0110] In an embodiment of the present invention, a clustering algorithm (such as K-means or hierarchical clustering) is used to perform cluster analysis on data on differences in silkworm environmental requirements. The algorithm uses the environmental requirement parameters of silkworms at various growth stages as input, and classifies them into clusters based on similarity. For example, the temperature requirements of silkworms at different growth stages are categorized into three types: high, medium, and low, and the humidity requirements are categorized into three types: high, medium, and low. Cluster analysis quantifies the differences in environmental requirements between different growth stages, generating clustered quantitative data on these differences. This data can help identify which silkworms at different growth stages require similar environmental conditions, thereby optimizing environmental control strategies.

[0111] Step S23: performing silkworm aggregation behavior recognition on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data;

[0112] In an embodiment of the present invention, a set of images of monitoring a silkworm breeding community is imported into a computer vision platform (such as OpenCV or TensorFlow). The aggregation behavior of silkworms is identified by an image recognition algorithm (such as YOLO or Mask R-CNN). The specific operation steps include: performing pre-processing such as denoising and grayscale adjustment on the monitoring image, using a trained aggregation behavior recognition model to detect and label the silkworms in the image, and identifying the aggregation area and aggregation degree of the silkworms. The recognition results are converted into structured data, and the aggregation behavior of the silkworms in each image is recorded, including the location of the aggregation area, the number of aggregated silkworms, and the aggregation degree. Through these steps, detailed silkworm aggregation behavior data is obtained to provide data support for the subsequent environmental interaction effect evaluation.

[0113] Step S24: evaluating the aggregation behavior-environment interaction effect between different silkworm growth stages based on the clustering quantification data of environmental demand differences according to the silkworm aggregation behavior data, and obtaining the aggregation behavior-environment interaction effect data.

[0114] In an embodiment of the present invention, the data on silkworm aggregation behavior and clustered quantitative data on differences in environmental requirements are imported into an environmental interaction effect evaluation platform. The impact of silkworm aggregation behavior on the environmental requirements of different growth stages is evaluated through statistical methods such as multiple regression analysis or factor analysis. For example, the impact of aggregation behavior on changes in local temperature and humidity is analyzed to assess whether these changes produce abnormal interactive effects on silkworms at different growth stages. If aggregation behavior causes a local temperature increase, it is assessed whether the larval silkworms can adapt to such environmental changes, and processing is performed for the subsequent environmental regulation of aggregation behavior.

[0115] Preferably, step S24 includes the following steps:

[0116] Step S241: performing aggregation density calculation on the silkworm aggregation behavior data to obtain silkworm aggregation density data; performing aggregation creep friction frequency calculation on the silkworm aggregation behavior data to obtain silkworm aggregation creep friction frequency data;

[0117] Step S242: performing aggregation temperature effect simulation based on the silkworm aggregation density data and the silkworm aggregation creep friction frequency data to obtain aggregation temperature effect simulation data;

[0118] Step S243: performing aggregation effect temperature increment calculation on the aggregation temperature effect simulation data to obtain aggregation effect temperature increment data;

[0119] Step S244: simulating the stress state of silkworms at different growth stages based on the clustered temperature increment data of the environmental demand difference clustering quantification data to obtain silkworm stress state simulation data;

[0120] Step S245: performing calculation on the silkworm stress state simulation data to determine the difference in silkworm vitality loss between different growth stages, and obtaining silkworm vitality loss difference data;

[0121] Step S246: Based on the aggregation effect temperature increment data, the silkworm stress state simulation data and the silkworm vitality loss difference data, the environmental demand difference clustering quantitative data is evaluated to obtain the aggregation behavior environment interaction effect data between different silkworm growth stages.

[0122] In an embodiment of the present invention, first, data on silkworm aggregation behavior is imported into a computing platform. Monitoring images are analyzed using image processing tools (such as OpenCV) to calculate the silkworm aggregation density in each image. Aggregation density can be expressed as the number of silkworms per unit area, for example, the number of silkworms per square centimeter. Then, a motion detection algorithm (such as optical flow) is used to analyze the silkworms' peristaltic behavior and calculate the peristaltic friction frequency of the silkworms within the aggregation area. Peristaltic friction frequency represents the number of times a silkworm rubs per unit time and is calculated by the inter-frame differences in an image sequence. Through these steps, detailed silkworm aggregation density data and aggregation peristaltic friction frequency data are obtained. Computational fluid dynamics (CFD) software (such as ANSYS Fluent) is used to simulate the aggregation temperature effect. First, the aggregation density data and peristaltic friction frequency data are input into a CFD model to establish a temperature field simulation of the silkworm aggregation area. The heat generated by friction is calculated based on the peristaltic friction frequency of the silkworms, and the temperature changes within the aggregation area are simulated using the CFD model. During the simulation, initial environmental temperature and humidity conditions were set to simulate the impact of silkworm aggregation on local temperature, generating simulated data on the aggregation temperature effect. Using the CFD simulation results, the temperature increment in the aggregation area was calculated. The temperature increment represents the local temperature increase caused by the aggregation and creeping friction of the silkworms. This involved extracting the temperature distribution of the aggregation area from the simulation data and calculating the average and maximum temperature increments. For example, if the initial temperature of a certain aggregation area was 25°C and the temperature increased to 28°C after simulation, the temperature increment would be 3°C. These steps generated the aggregation-effect temperature increment data. The aggregation-effect temperature increment data and the quantitative clustering data on environmental demand differences were imported into the stress state simulation platform. Physiological models (such as metabolic models) were used to simulate the stress state of silkworms at different growth stages under the temperature changes caused by aggregation behavior. The stress state simulation included physiological responses, metabolic changes, and behavioral changes in the silkworms. For example, under conditions of large temperature increments, changes in respiratory rate, heart rate, and activity frequency were simulated for silkworms at different growth stages. Through these simulations, simulated stress state data for silkworms at different growth stages were generated. Using stress state simulation data, the vitality loss of silkworms at different growth stages is calculated. Vitality loss can be measured by indicators such as the activity frequency, feed intake, and growth rate of silkworms. For example, under stress, the activity frequency of silkworms decreases, feed intake decreases, and weight gain slows. By comparing these indicators of silkworms at different growth stages, the differences in their vitality loss are calculated, and the difference data on silkworm vitality loss are obtained. The aggregation effect temperature increment data, silkworm stress state simulation data, and silkworm vitality loss difference data are integrated into the evaluation platform. Using multiple regression analysis or factor analysis, the environmental interaction effects of silkworms at different growth stages under aggregation behavior are evaluated. For example, the impact of the temperature increase caused by the aggregation behavior of silkworms on the stress state and vitality loss of silkworms at each stage is analyzed, and its comprehensive effect is evaluated.Through these assessments, cluster behavior-environment interaction effect data were obtained.

[0123] Preferably, calculating the variance of vitality loss between different silkworm growth stages for silkworm stress state simulation data comprises the following steps:

[0124] The slowness of silkworm peristalsis frequency between different silkworm growth stages is evaluated based on the simulated data of silkworm stress state, and the slowness of silkworm peristalsis frequency data is obtained;

[0125] The slowdown fluctuation interval of silkworm peristalsis frequency at different growth stages was calculated based on the slowdown data of silkworm peristalsis frequency, and the slowdown fluctuation interval of silkworm peristalsis frequency was obtained.

[0126] According to the slow fluctuation interval of peristalsis frequency, the slow fluctuation logarithm transformation is performed on the peristalsis frequency data of silkworms to obtain the slow fluctuation logarithm transformation data;

[0127] The skewness of the slowing time series distribution is analyzed on the logarithmic transformation data of slowing fluctuations to obtain the skewness of the slowing time series distribution data;

[0128] According to the skewness data of the slowing time series distribution, the slowing numerical value approximate interval is calculated for the slowing fluctuation logarithm transformation data, and the slowing numerical value approximate interval is obtained;

[0129] Based on the grey correlation method and the approximate interval of the slowing value, the nonlinear slowing constraint analysis of the peristaltic frequency slowing fluctuation interval was carried out to obtain the peristaltic frequency slowing correlation data.

[0130] The difference in silkworm vitality loss between different growth stages was calculated based on the correlation data of peristalsis frequency slowing down, and the difference in silkworm vitality loss data was obtained.

[0131] In an embodiment of the present invention, simulated data on silkworm stress states is imported into a statistical analysis platform (such as MATLAB or R). The peristaltic frequency of silkworms at different growth stages is evaluated. Specifically, a time series analysis method is used to analyze the trend of peristaltic frequency changes in different growth stages and regions, and the rate of change of peristaltic frequency is calculated. During the evaluation process, a linear regression model is used to fit the temporal trend of peristaltic frequency to obtain peristaltic frequency bradycardia data. This peristaltic frequency bradycardia data is then used to calculate the fluctuation range of peristaltic frequency at different growth stages. Specifically, a statistical analysis tool (such as the Python Pandas library) is used to calculate the standard deviation and mean of peristaltic frequency for each growth stage to generate the fluctuation range. For example, if the peristaltic frequency bradycardia data for a particular growth stage has a mean of 5 beats / minute and a standard deviation of 1 beat / minute, then the fluctuation range is 4-6 beats / minute. These calculations yield the peristaltic frequency bradycardia fluctuation range data. The peristaltic frequency bradycardia fluctuation range data is then logarithmically transformed to reduce data volatility and scale differences. The specific operation is: take the natural logarithm (log) of the fluctuation interval data. For example, if the fluctuation interval is 4-6 times / minute, the logarithm is converted to ln(4) to ln(6). Through these steps, the logarithmic transformation data of the slow fluctuation is obtained. The logarithmic transformation data is used to perform time series distribution skewness analysis. The specific operation is: use time series analysis tools (such as Python's statsmodels library) to calculate the time series distribution skewness (such as skewness and kurtosis) of the peristalsis frequency slowing data in each growth stage. For example, the skewness of the peristalsis frequency slowing data of a certain growth stage is calculated to be 0.5 and the kurtosis is 3.2, indicating the degree of skewness of its time series distribution. Through these calculations, the skewness data of the slowing time series distribution is obtained. Based on the skewness data of the slowing time series distribution, the numerical approximate interval of the slowing fluctuation logarithmic transformation data is calculated. The specific operation is: use statistical tools (such as Python's NumPy library) to calculate the numerical approximate interval (such as 95% confidence interval) of the slowing fluctuation logarithmic transformation data. For example, the 95% confidence interval for the logarithmically transformed data of the slowing fluctuations at a certain growth stage is [1.3, 2.5], representing the range of its numerical distribution. These calculations yielded the approximate numerical interval for the slowing. The gray correlation method was used to perform a nonlinear slowing constraint analysis on the approximate numerical interval for the slowing fluctuations and the approximate numerical interval for the peristaltic frequency. Specifically, the correlation between the slowing fluctuation interval and the approximate numerical interval was calculated using gray system theory (such as the GRA algorithm). The correlation reflects the strength of the relationship between the two datasets. For example, a correlation of 0.85 for a certain growth stage indicates a strong relationship between the slowing fluctuation interval and the approximate numerical interval. These calculations yielded the peristaltic frequency slowing correlation data. This peristaltic frequency slowing correlation data was used to calculate the differences in vitality loss among silkworms at different growth stages.The specific operation is to compare the correlation data of peristalsis frequency slowing at different growth stages and evaluate the difference in vitality loss at each stage. For example, if the correlation is 0.85 in one stage and 0.75 in another, the difference in vitality loss is calculated to be 0.10. Through these comparisons, the difference in vitality loss of mulberry silkworms is obtained.

[0132] Preferably, step S3 includes the following steps:

[0133] Step S31: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; wherein the behavior-environment demand regulation data includes behavior-environment temperature regulation data and behavior-environment airflow regulation data;

[0134] Step S32: Calculating the impact of the silkworm breeding gathering behavior on the adjacent activity area based on the behavior activity environment demand control data to obtain the adjacent activity area environmental impact data;

[0135] Step S33: identifying the degree of azimuth distribution environmental impact of the silkworm breeding aggregation behavior in the vicinity of the activity area based on the environmental impact data of the vicinity of the activity area, and obtaining the azimuth distribution environmental impact degree data;

[0136] Step S34: performing intelligent control optimization of the global balance of the environment for silkworm breeding based on the azimuth distribution environmental impact degree data and the behavioral activity environmental demand regulation data to obtain environmental intelligent control optimization data.

[0137] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0138] Step S31: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; wherein the behavior-environment demand regulation data includes behavior-environment temperature regulation data and behavior-environment airflow regulation data;

[0139] In an embodiment of the present invention, data on the interaction between clustering behavior and the environment is imported into an environmental control system (such as MATLAB or Python). Using a multivariate regression analysis method, the environmental requirements of silkworms' activities are regulated based on their environmental requirements. This involves analyzing the changes in temperature and airflow requirements for clustering behavior during different growth stages. Through regression analysis, a mathematical model of behavioral activity and environmental requirements is established, generating temperature control data and airflow control data for these activities. For example, the analysis results indicate that under high-density clustering conditions, silkworms require a temperature of 28°C and an airflow of 2 meters per second. (For example, during silkworm rearing, data on the interaction between clustering behavior and the environment indicate that high density clustering leads to elevated temperatures in certain areas during the fifth instar stage. Regression analysis determines that the optimal growth temperature for silkworms at this stage, when clustered at high density, is 28°C, and the optimal airflow velocity is 2 meters per second. Therefore, the temperature control data for these activities is 28°C, and the airflow control data is 2 meters per second.)

[0140] Step S32: Calculating the impact of the silkworm breeding gathering behavior on the adjacent activity area based on the behavior activity environment demand control data to obtain the adjacent activity area environmental impact data;

[0141] In an embodiment of the present invention, first, a spatial distribution map of the silkworm rearing area is created using Geographic Information System (GIS) software, marking the specific locations where aggregation behavior occurs. Then, based on the behavioral activity environmental demand control data obtained in step S31, heat conduction and fluid dynamics models are used to simulate the impact of aggregation behavior on the surrounding environment. Specifically, computational fluid dynamics (CFD) software, such as ANSYS Fluent, can be used to construct a three-dimensional model and perform numerical simulations. The simulation results will display the spatial distribution changes of environmental factors such as temperature, humidity, and airflow. By comparing the simulation results with the original environmental data, the environmental impact on the adjacent activity area can be quantified and calculated, thereby obtaining the environmental impact data for the adjacent activity area. (For example, using ANSYS Fluent software, the behavioral activity temperature control data of 28°C and the airflow control data of 2 m / s are input into the simulation model. The simulation results show that the temperature impact of the silkworm aggregation area on the adjacent activity area ranges from 27°C to 29°C, and the airflow velocity ranges from 1.8 to 2.2 m / s. Therefore, the environmental impact data for the adjacent activity area is a temperature of 27°C to 29°C and an airflow velocity of 1.8 to 2.2 m / s.)

[0142] Step S33: identifying the degree of azimuth distribution environmental impact of the silkworm breeding aggregation behavior in the vicinity of the activity area based on the environmental impact data of the vicinity of the activity area, and obtaining the azimuth distribution environmental impact degree data;

[0143] In an embodiment of the present invention, it is necessary to further analyze the environmental impact data of the adjacent activity area to identify the degree of environmental impact in different directions. First, the environmental impact data obtained in step S32 is imported into professional spatial analysis software, such as ArcGIS. The spatial interpolation function of the software is used to generate a continuous distribution surface of environmental impact. Then, with the point where the aggregation behavior occurs as the center, the surrounding area is divided into several azimuth sectors (such as eight directions of east, southeast, south, southwest, west, northwest, north, and northeast). The degree of environmental impact in each sector is statistically analyzed, and indicators such as the average value, maximum value, and minimum value are calculated. In addition, hot spot analysis tools can also be used to identify areas where the environmental impact is particularly significant. Finally, these analysis results are integrated to form a detailed azimuth distribution environmental impact data report, including the impact degree ranking, impact range, and impact intensity information of each direction. (For example, using ArcGIS software, the environmental impact data of adjacent activity areas are mapped onto the azimuth map of the silkworm breeding area. The analysis results show that the temperature change in the south is the most significant, with a temperature increment of 2°C and an airflow velocity increment of 0.5 m / s. Therefore, the azimuth distribution environmental impact degree data is a temperature increment of 2°C and an airflow velocity increment of 0.5 m / s in the south).

[0144] Step S34: performing intelligent control optimization of the global balance of the environment for silkworm breeding based on the azimuth distribution environmental impact degree data and the behavioral activity environmental demand regulation data to obtain environmental intelligent control optimization data.

[0145] In an embodiment of the present invention, data on the degree of environmental impact of azimuth distribution and data on the regulation of environmental requirements for behavioral activities are input into an intelligent control system (e.g., an AI-based control algorithm). Specifically, the intelligent control algorithm (e.g., a reinforcement learning algorithm) is used to perform global balance optimization of the silkworm rearing environment. Based on the input data, the system dynamically adjusts the temperature and airflow in the rearing environment to achieve optimal equilibrium in all directions. For example, the intelligent control system adjusts the temperature in the south direction to 28°C and maintains an airflow speed of 2 meters per second to ensure an optimal growth environment for silkworms at all stages of growth. Through these optimization operations, optimized intelligent environmental control data is generated to guide silkworm rearing. (For example, data indicating a 2°C temperature increment and a 0.5 m / s airflow speed increment in the south direction is input into the intelligent control system. Using the reinforcement learning algorithm, the intelligent control system adjusts the temperature in the south direction to 28°C and maintains an airflow speed of 2 meters per second to ensure an optimal growth environment for silkworms at all stages of growth. After optimization, the optimized intelligent environmental control data is a 28°C temperature and a 2 m / s airflow speed in the south direction.)

[0146] Preferably, step S31 includes the following steps:

[0147] Step S311: analyzing abnormal temperature fluctuations in aggregation behavior during silkworm rearing based on the aggregation behavior-environment interaction effect data to obtain abnormal temperature fluctuation data in aggregation behavior;

[0148] Step S312: evaluating the temperature fluctuation tolerance of silkworms at different growth stages based on the abnormal temperature fluctuation data of the aggregation behavior and the difference data of the silkworms' environmental requirements, to obtain the temperature fluctuation tolerance data of the silkworms;

[0149] Step S313: simulating the air circulation of the aggregation behavior during the silkworm breeding process according to the aggregation behavior-environment interaction effect data to obtain aggregation behavior air circulation data;

[0150] Step S314: analyzing the air duct barrier effect of the clustering behavior during the silkworm breeding process on the clustering behavior air circulation data to obtain the clustering behavior air duct barrier effect data;

[0151] Step S315: performing demand difference data pairing on the silkworm environmental demand difference data according to the silkworm temperature fluctuation tolerance data and the gathering behavior air duct barrier effect data to obtain environmental demand difference paired data;

[0152] Step S316: performing behavior activity environment demand regulation based on the paired data according to the environmental demand difference, and obtaining behavior activity environment demand regulation data; wherein the behavior activity environment demand regulation data includes behavior activity temperature regulation data and behavior activity airflow regulation data.

[0153] In this embodiment of the present invention, data analysis software (such as the Python pandas library) is used to process data on the interaction effect of aggregation behavior and environment. A temperature sensor network and data analysis software are then used to analyze abnormal temperature fluctuations in aggregation behavior during different growth stages of silkworm rearing. First, multiple high-precision temperature sensors (such as PT100) are placed in the rearing area to ensure full coverage, particularly in areas where silkworms are likely to aggregate. These sensors record temperature data every minute. A data processing script is written in Python. The average temperature for the entire area is calculated as a baseline, and then areas and time points where the temperature deviates significantly from the average are identified. For example, if the temperature in a certain area exceeds the average by more than 2°C and persists for more than 30 minutes, it is marked as an abnormal temperature fluctuation event. The frequency, duration, and spatial distribution of these events are also analyzed, as well as their correlation with silkworm aggregation behavior. Finally, a detailed report on abnormal temperature fluctuations in aggregation behavior is generated, including information such as the time, location, amplitude, and duration of the fluctuations. This allows for analysis of abnormal temperature fluctuations in aggregation behavior during silkworm rearing. Alternatively, the temperature data can be arranged in a time series, and the normal temperature variation trend can be calculated using a moving average method. Next, the difference between the actual temperature and the moving average is calculated, and a threshold (e.g., ±1.5°C) is set to identify abnormal fluctuations. For example, if the actual temperature at a certain point in time is 2°C higher than the moving average, this is flagged as an abnormally high temperature event. Time series analysis methods (e.g., ARIMA models) can also be used to predict normal temperature fluctuations, and the predicted values ​​can be compared with the actual values ​​to identify anomalies. Finally, the frequency, duration, and magnitude of abnormal events are statistically analyzed to generate a data report on clustered abnormal temperature fluctuations. Based on the clustered abnormal temperature fluctuation data obtained in S311, the temperature fluctuation tolerance of silkworms at different growth stages is assessed. The silkworm growth cycle is divided into five stages: 1st, 2nd, 3rd, 4th, and 5th instar. For each stage, a series of temperature fluctuation experiments are designed. In these experiments, a precision temperature-controlled chamber is used to simulate temperature fluctuations of varying degrees (e.g., ±1°C, ±2°C, ±3°C) for 1, 3, and 6 hours, respectively. During each experiment, the silkworms' physiological indicators (such as survival rate and molting rate) and behavioral changes (such as food intake and activity frequency) were observed and recorded. Data were analyzed using SPSS statistical software, and the tolerance index for each growth stage under different temperature fluctuation conditions was calculated. For example, it was found that fourth-instar silkworms had a high tolerance to temperature fluctuations of ±2°C, while first-instar silkworms were more sensitive to the same fluctuations. Ultimately, a detailed data report on the temperature fluctuation tolerance of silkworms at different growth stages was generated, providing an important basis for subsequent environmental control. To understand the impact of silkworm aggregation behavior on air circulation during silkworm rearing, data on the interaction between aggregation behavior and environment were first collected.This data, typically obtained through sensor networks and image processing techniques, includes environmental parameters such as silkworm density, peristalsis frequency, temperature, and humidity. A three-dimensional CFD model is constructed based on the actual size and layout of the silkworm rearing environment. The model defines the air circulation paths within and around the silkworm clustering area. Data on the interaction between clustering behavior and the environment are input into the CFD model. This includes parameters such as density distribution and temperature variations within the clustering area. Boundary conditions are set within the model, such as air velocity, temperature, and humidity at the inlet and outlet. A CFD simulation is run to analyze the air flow within the clustering area. During the simulation, data such as air velocity, direction, and pressure distribution within the clustering area are calculated. Key data is extracted from the CFD simulation results to derive air circulation data on clustering behavior. For example, the simulation results show that air velocity decreases significantly in high-density clustering areas, falling to 0.3 m / s, while in low-density areas, the air velocity remains at 0.6 m / s. Based on the air circulation data obtained in step S313, further analysis is performed to assess the obstruction effect of silkworm clustering on the air ducts of the breeding environment. The air circulation data obtained from the CFD simulation is processed to extract key parameters such as air velocity, flow direction, and pressure distribution. This data is then correlated with factors such as the silkworm's cluster density and peristalsis frequency. By analyzing the air circulation data, the obstruction effect of the silkworm clustering areas on the air ducts is identified. For example, in high-density clustering areas, the air flow velocity decreases significantly, indicating that this area has a obstruction effect on the air ducts. The degree of obstruction caused by clustering on the air ducts is quantified. A specific method involves calculating the change in air flow velocity at different cluster densities. For example, in high-density clustering areas, the air flow velocity decreases from 0.6 m / s to 0.3 m / s, resulting in a 50% obstruction. The impact of the air duct obstruction effect of clustering on the silkworm breeding environment is assessed. The analysis results show that the air duct obstruction effect in high-density clustering areas leads to poor air circulation, causing local temperature increases and humidity changes, thereby affecting the silkworm's growth environment. Collect data on silkworms' tolerance to temperature fluctuations. This data includes the silkworms' tolerance range and response to temperature changes at different growth stages. For example, the early larval stage has a lower tolerance to temperature fluctuations, while the mature stage has a higher tolerance. Integrate the data on the air duct barrier effect of aggregation behavior obtained in the previous step into the environmental demand analysis. This data includes the barrier effect of different aggregation behaviors on air ducts and the corresponding changes in air circulation. Use data analysis tools (such as the pandas library in R or Python) to perform paired analysis on the temperature fluctuation tolerance data and the air duct barrier effect data. Use multiple regression analysis or machine learning algorithms to find the correlation between the two sets of data. For example, in the growth stage with low tolerance to temperature fluctuations, when the air duct barrier effect is significant, special attention should be paid to the regulation of temperature and airflow. Based on the results of the paired analysis, generate paired data on environmental demand differences.For example, paired data indicates that the early larval stage requires higher airflow and a more stable temperature environment, while the mature stage requires moderate airflow and temperature regulation. Based on the paired data and the differences in environmental requirements, control targets are set for each growth stage. For example, for the early larval stage, the goal is to maintain a temperature of around 25°C and an airflow velocity of at least 0.5 m / s. Appropriate environmental control equipment should be selected, including temperature control devices (such as thermostats, heaters, and cooling equipment) and airflow control devices (such as fans and ventilation systems). Ensure that these devices can be adjusted in real time to meet the environmental requirements of different stages. A sensor network is used to monitor the temperature and airflow data of the silkworm rearing environment in real time. Sensors can be installed at various locations within the silkworm rearing box to ensure comprehensive and accurate data. Based on real-time monitoring data and pre-set control targets, a control system (such as a PLC or DCS system) automatically adjusts temperature and airflow. For example, when the monitoring data indicates that the temperature exceeds the target value, the control system automatically activates the cooling equipment; when the airflow velocity falls below the target value, the fan is automatically activated. All data during the control process is recorded and regularly analyzed to evaluate the control effectiveness and the growth status of the silkworms. Through data analysis, the control strategy can be further optimized to ensure the best environmental conditions.

[0154] Preferably, step S34 includes the following steps:

[0155] Step S341: performing an environmental impact time lag effect analysis on the adjacent activity areas of the silkworm breeding aggregation behavior based on the azimuth distribution environmental impact degree data to obtain distribution environmental impact time lag effect data;

[0156] Step S342: extracting the environmental temperature mutation and analyzing the airflow structure of the area adjacent to the silkworm breeding gathering behavior based on the temperature control data of the behavior activity, the airflow control data of the behavior activity, and the time lag effect data of the distribution environment, to obtain the azimuthally distributed environmental temperature mutation data and the azimuthally distributed airflow structure data;

[0157] Step S343: identifying the spatial distribution mutation and progressive law of the adjacent activity areas of the silkworm breeding and aggregation behavior based on the azimuth distribution environmental temperature mutation data to obtain temperature distribution mutation and progressive law data;

[0158] Step S344: performing intelligent control optimization of the global temperature balance of silkworm rearing based on the temperature distribution mutation and progressive law data and the behavior and activity environment demand control data to obtain temperature balance intelligent control optimization data;

[0159] Step S345: performing an airflow stacking effect analysis on the azimuthally distributed airflow flow structure data for the adjacent activity areas of the silkworm breeding aggregation behavior to obtain azimuthally distributed airflow stacking effect data;

[0160] Step S346: performing intelligent control optimization of the global balance of airflow for silkworm breeding based on the azimuth distribution airflow stacking effect data and the behavioral activity environment demand control data to obtain airflow balance intelligent control optimization data;

[0161] Step S347: performing global balance intelligent control optimization of the silkworm breeding environment according to the temperature balance intelligent control optimization data and the airflow balance intelligent control optimization data to obtain environmental intelligent control optimization data.

[0162] In an embodiment of the present invention, data on the degree of environmental impact at each location is first collected. This data includes changes in environmental parameters such as temperature, humidity, and airflow velocity at different locations within a silkworm rearing box. A suitable time-lag effect analysis tool, such as time series analysis software (e.g., MATLAB's Time Series Toolbox) or a specialized environmental data analysis platform, is then selected and used to perform a time-lag effect analysis on the environmental impact data. Cross-correlation analysis is used to determine the relationship between changes in environmental parameters at different locations and time, identifying time lags in environmental parameter changes. For example, a temperature change at one location affects temperature changes at adjacent locations 10 minutes later. The analysis results are extracted to generate distributed environmental impact time-lag effect data. This data details the environmental parameter changes at each location and their time-lag effects. For example, a temperature change at one location can affect the temperature at adjacent locations with a 10-minute lag, while a humidity change can affect the temperature at adjacent locations with a 15-minute lag. The behavioral activity temperature control data, airflow control data, and distributed environmental impact time-lag effect data are then integrated to ensure data consistency and integrity. A temperature monitoring sensor network is used to monitor and record temperature data at each location within the silkworm rearing box in real time. Use statistical analysis tools (such as the changepoint package in R) to analyze temperature data for sudden changes and identify temperature abrupt changes. For example, consider a temperature change at a specific location from 25°C to 30°C over a short period of time. Use fluid dynamics simulation software (such as ANSYS Fluent) to analyze the airflow structure within the silkworm rearing environment. Input airflow control data and time-lag effect data into a simulation model to simulate the flow path and velocity distribution of airflow within the rearing environment. This simulation identifies areas of poor airflow and potential airflow obstructions. Based on the results of sudden change extraction and flow structure analysis, generate location-based ambient temperature abrupt changes and location-based airflow structure data. For example, record the temperature abrupt changes and their magnitudes at specific locations within the rearing box, as well as the locations of airflow obstructions along the airflow path. Integrate the previously generated location-based ambient temperature abrupt changes to ensure data coverage of all important areas within the silkworm rearing box. Select appropriate tools for analyzing progressive patterns, such as geographic information system (GIS) analysis software or time-space analysis tools (such as Space-Time Cube). Use selected analysis tools to identify spatial distribution patterns in temperature mutation data. By analyzing the spatial distribution of temperature mutation points and their temporal variations, the path and patterns of temperature mutation progression can be identified. For example, the time and magnitude of temperature changes in adjacent areas following a temperature mutation in one region can be analyzed to determine the propagation path of the temperature mutation. Based on the analysis results, data on temperature mutation progression patterns are generated. This data details the temporal and spatial distribution of temperature mutations and their propagation paths. For example, the magnitude and direction of temperature changes in adjacent areas within 5 minutes following a temperature mutation in one region can be recorded.Integrate previously acquired data on temperature distribution mutations and progression patterns with data on behavioral and activity environment demand regulation. Ensure the comprehensiveness and accuracy of the data, including temperature variations at all locations and the temperature requirements of silkworms at different stages. Select an appropriate optimization tool, such as the MATLAB Optimization Toolbox or specialized environmental control optimization software. Build a global temperature balance model. Use the optimization tool to input the integrated data and simulate temperature variations in the silkworm rearing environment. Adjust model parameters to optimize the temperature control strategy, ensuring temperature balance at all locations and avoiding local overheating or overcooling. For example, global temperature balance can be achieved by adjusting the operating parameters of the ventilation, heating, or cooling systems. Extract the optimized temperature control strategy data to generate temperature balance intelligent control optimization data. This data details each control parameter and its setting value, such as the ventilation system's air velocity and the heating system's temperature setpoint. Collect azimuthally distributed airflow structure data to ensure coverage of airflow data at all important locations in the silkworm rearing environment. Select an appropriate airflow stacking effect analysis tool, such as fluid dynamics simulation software (such as ANSYS Fluent) or an airflow analysis platform, and use the selected tool to analyze the airflow structure data and identify airflow stacking effects. For example, by simulating the flow path of airflow in a breeding environment, areas of airflow accumulation and their impact range can be identified. The analysis results are extracted to generate azimuthally distributed airflow stacking effect data. This data details the airflow stacking phenomenon and its impact in each direction, such as recording parameters such as the velocity and pressure of airflow accumulation in a specific direction. The azimuthally distributed airflow stacking effect data is integrated with the behavioral activity environment demand control data. To ensure the comprehensiveness and accuracy of the data, including the airflow conditions in each direction and the airflow requirements of silkworms at different stages, appropriate optimization tools are selected, such as MATLAB's optimization toolbox or professional environmental control optimization software. A global airflow balance model is established. The integrated data is input using the optimization tool to simulate airflow changes in the silkworm breeding environment. Model parameters are adjusted to optimize the airflow control strategy, ensure airflow balance, and avoid local airflow accumulation or insufficient airflow. For example, by adjusting the operating parameters of the ventilation system to achieve global airflow balance, the optimized airflow control strategy data is extracted to generate airflow balance intelligent control optimization data. This data details each control parameter and its setting value, such as the wind speed setpoint for the ventilation system. Through these steps, we ensure airflow balance in the silkworm rearing environment, implement intelligent airflow control, and provide the most suitable airflow conditions. We also integrate the temperature balance intelligent control optimization data and the airflow balance intelligent control optimization data. Ensure the comprehensiveness and consistency of the data, including the optimized parameters for temperature and airflow. Select an appropriate comprehensive optimization tool, such as MATLAB's multi-objective optimization toolbox or professional environmental control optimization software. Establish a global environmental balance model. Use the optimization tool to input the integrated data and comprehensively simulate the temperature and airflow changes in the silkworm rearing environment.Adjust model parameters to achieve an optimal control strategy for global environmental balance. For example, by jointly adjusting the operating parameters of the ventilation, heating, and cooling systems, global environmental optimization is achieved. The optimized environmental control strategy data is extracted to generate intelligent environmental control optimization data. This data details the individual integrated control parameters and their settings, such as the combined operating parameters of the ventilation, heating, and cooling systems. Through these steps, the optimal balance of temperature and airflow in the silkworm rearing environment is achieved, achieving global intelligent environmental control and providing optimal growth conditions.

[0163] Preferably, performing intelligent control optimization of airflow global balance on behavioral activity environment demand regulation data based on azimuth distribution airflow stacking effect data includes the following steps:

[0164] The airflow backflow path simulation of the adjacent activity area of ​​mulberry silkworm feeding aggregation behavior was carried out on the azimuthally distributed airflow stacking effect data to obtain the airflow backflow path simulation data;

[0165] The difficulty of airflow exchange and diffusion is evaluated based on the azimuthal distribution airflow stacking effect data based on the airflow return path simulation data to obtain the airflow exchange and diffusion difficulty data;

[0166] Optimize the airflow direction angle control based on the airflow exchange and diffusion difficulty data to obtain airflow direction angle control data;

[0167] Performing airflow velocity control adaptation on the airflow exchange and diffusion difficulty data according to the airflow direction angle control data to obtain airflow velocity control adaptation data;

[0168] Based on the airflow direction angle control data, airflow velocity control adaptation data and behavioral activity environment demand regulation data, the global airflow balance intelligent control optimization of silkworm breeding is carried out to obtain the airflow balance intelligent control optimization data.

[0169] In an embodiment of the present invention, data on the airflow stacking effect at different locations in a silkworm rearing environment is collected, including airflow velocity, direction, and pressure distribution. The collected data is analyzed using fluid dynamics simulation software (such as ANSYS Fluent) to create a three-dimensional model of the rearing environment. The airflow stacking effect data is input into the software and a recirculation path simulation is run. Through the simulation, the airflow path within the rearing environment is observed, with particular attention paid to recirculation areas and airflow convergence points. The recirculation path simulation data is recorded and extracted, showing the recirculation paths and their impact areas at various locations. The recirculation path simulation data is integrated with the airflow stacking effect data to ensure comprehensiveness and accuracy. Using an airflow analysis platform or a custom-written evaluation algorithm, the integrated data is used to assess the difficulty of airflow exchange and diffusion. The exchange and diffusion of airflow within each recirculation path is analyzed to assess the exchange difficulty of airflow in different areas. For example, this can assess whether airflow in a particular area is affected by obstacles, resulting in exchange difficulties. Airflow exchange and diffusion difficulty data is generated, recording the exchange difficulty level for each location. Appropriate optimization tools, such as the MATLAB Optimization Toolbox or specialized airflow control optimization software, are selected. Adjust airflow angles to optimize airflow direction, ensuring smoother exchange and diffusion of air in all directions. For example, optimize airflow direction by adjusting the angle and position of vents. Generate airflow angle control data and record the optimized airflow angle settings. Integrate the airflow angle control data with the airflow exchange and diffusion difficulty data to ensure data comprehensiveness and accuracy. Select an appropriate flow rate control adaptation tool, such as fluid dynamics optimization software or MATLAB's Control System Toolbox. Use the adaptation tool to input the integrated data and establish an airflow rate control adaptation model. Through simulation and calculation, find the optimal airflow rate settings to meet the airflow exchange and diffusion requirements of different areas. Generate airflow rate control adaptation data, detailing the airflow rate settings for each area. Through these steps, optimize airflow rates in the silkworm rearing environment, ensure smooth airflow, and improve ventilation effectiveness. Integrate the airflow angle control data, airflow rate control adaptation data, and behavioral activity environment demand regulation data to ensure data comprehensiveness and consistency. Establish a global airflow balance model. Use the optimization tool to input the integrated data and comprehensively simulate airflow changes in the silkworm rearing environment. Adjust model parameters to achieve global airflow balance and intelligent control optimization. Generate airflow balance intelligent control optimization data, detailing the comprehensive operating parameters and settings of each system, such as the ventilation system's wind speed, direction, and operating duration. Through these steps, the airflow in the silkworm rearing environment is optimally balanced, achieving global intelligent airflow control and providing the most suitable airflow conditions.

[0170] Preferably, the present invention further provides an intelligent environmental control system for silkworm breeding, which is used to execute the intelligent environmental control method for silkworm breeding as described above. The intelligent environmental control system for silkworm breeding comprises:

[0171] The silkworm growth stage classification module is used to obtain the silkworm growth cycle data; perform real-time monitoring of the silkworm breeding community to obtain a set of silkworm breeding community monitoring images; classify the silkworm breeding community monitoring image set according to the silkworm growth cycle data to obtain the silkworm growth stage data;

[0172] The silkworm aggregation behavior environment analysis module is used to analyze the environmental demand differences between different silkworms based on the data of silkworm growth stages, and obtain the silkworm environmental demand difference data; identify the silkworm aggregation behavior based on the silkworm breeding community monitoring image set, and obtain the silkworm aggregation behavior data; and evaluate the aggregation behavior environment interaction effect between different silkworm growth stages based on the silkworm environmental demand difference data, and obtain the aggregation behavior environment interaction effect data;

[0173] The global control optimization module for silkworm rearing is used to regulate the environmental demand of silkworms' behavior activities based on the aggregated behavior-environment interaction effect data, and obtain the behavior-environment demand regulation data; and to optimize the global balance of the silkworm rearing environment intelligent control based on the behavior-environment demand regulation data, and obtain the environmental intelligent control optimization data;

[0174] The control management strategy execution module is used to design an automated mulberry silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the mulberry silkworm breeding environment control management strategy, and send the mulberry silkworm breeding environment control management strategy to the cloud platform to execute the mulberry silkworm breeding intelligent environment control.

[0175] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0176] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent environment control method for silkworm breeding, characterized in that: The following steps are involved: Step S1: acquiring silkworm growth cycle data; performing real-time monitoring on a silkworm breeding community to obtain a set of monitoring images of the silkworm breeding community; classifying the set of monitoring images of the silkworm breeding community according to the silkworm growth cycle data to obtain data on the growth stage of the silkworm; Step S2 includes: Step S21: performing an analysis on the environmental requirements differences between different silkworm growth stages based on the silkworm growth cycle data to obtain silkworm environmental requirements difference data; Step S22: performing stage-by-stage clustering difference quantification on the silkworm environmental demand difference data to obtain environmental demand difference clustering quantification data; Step S23: performing silkworm aggregation behavior recognition on the silkworm breeding community monitoring image set to obtain silkworm aggregation behavior data; Step S24: evaluating the interaction effect of aggregation behavior and environment between different silkworm growth stages based on the clustered quantitative data of environmental demand differences according to the aggregation behavior data of silkworms, and obtaining the aggregation behavior and environment interaction effect data; specifically: Step S241: performing aggregation density calculation on the silkworm aggregation behavior data to obtain silkworm aggregation density data; performing aggregation creep friction frequency calculation on the silkworm aggregation behavior data to obtain silkworm aggregation creep friction frequency data; Step S242: performing aggregation temperature effect simulation based on the silkworm aggregation density data and the silkworm aggregation creep friction frequency data to obtain aggregation temperature effect simulation data; Step S243: performing aggregation effect temperature increment calculation on the aggregation temperature effect simulation data to obtain aggregation effect temperature increment data; Step S244: simulating the stress state of silkworms at different growth stages based on the clustered temperature increment data of the environmental demand difference clustering quantification data to obtain silkworm stress state simulation data; Step S245: performing calculation on the silkworm stress state simulation data to determine the difference in silkworm vitality loss between different growth stages, and obtaining silkworm vitality loss difference data; Step S246: evaluating the aggregation behavior-environment interaction effect between different silkworm growth stages based on the aggregation effect temperature increment data, the silkworm stress state simulation data, and the silkworm vitality loss difference data on the environmental demand difference clustering quantification data to obtain the aggregation behavior-environment interaction effect data; Step S3 includes: Step S31: regulating the environmental demand of silkworms according to the aggregated behavior-environment interaction effect data to obtain behavior-environment demand regulation data; wherein the behavior-environment demand regulation data includes behavior-environment temperature regulation data and behavior-environment airflow regulation data; Step S32: Calculating the impact of the silkworm breeding gathering behavior on the adjacent activity area based on the behavior activity environment demand control data to obtain the adjacent activity area environmental impact data; Step S33: identifying the degree of azimuth distribution environmental impact of the silkworm breeding aggregation behavior in the vicinity of the activity area based on the environmental impact data of the vicinity of the activity area, and obtaining the azimuth distribution environmental impact degree data; Step S34: performing intelligent control optimization of the global balance of the silkworm breeding environment based on the azimuth distribution environmental impact degree data and the behavioral activity environmental demand regulation data to obtain environmental intelligent control optimization data; Step S4: Design an automated silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the silkworm breeding environment control management strategy, and send the silkworm breeding environment control management strategy to the cloud platform to execute the silkworm breeding intelligent environment control.

2. The intelligent environment control method for silkworm breeding according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire silkworm growth cycle data; Step S12: real-time monitoring of the silkworm breeding colony is performed using electronic monitoring equipment to obtain a set of monitoring images of the silkworm breeding colony; Step S13: performing image sharpening processing on the silkworm breeding colony monitoring image set to obtain a silkworm colony monitoring sharpened image set; Step S14: classifying the silkworm colony monitoring sharpened image set according to the silkworm growth cycle data to obtain the silkworm growth stage data.

3. The intelligent environment control method for silkworm breeding according to claim 1, characterized in that: Calculating the variance of vitality loss between different silkworm growth stages for silkworm stress state simulation data includes the following steps: The slowness of silkworm peristalsis frequency between different silkworm growth stages is evaluated based on the simulated data of silkworm stress state, and the slowness of silkworm peristalsis frequency data is obtained; The slowdown fluctuation interval of silkworm peristalsis frequency at different growth stages was calculated based on the slowdown data of silkworm peristalsis frequency, and the slowdown fluctuation interval of silkworm peristalsis frequency was obtained. According to the slow fluctuation interval of peristalsis frequency, the slow fluctuation logarithm transformation is performed on the peristalsis frequency data of silkworms to obtain the slow fluctuation logarithm transformation data; The skewness of the slowing time series distribution is analyzed on the logarithmic transformation data of slowing fluctuations to obtain the skewness of the slowing time series distribution data; According to the skewness data of the slowing time series distribution, the slowing numerical value approximate interval is calculated for the slowing fluctuation logarithm transformation data, and the slowing numerical value approximate interval is obtained; Based on the grey correlation method and the approximate interval of the slowing value, the nonlinear slowing constraint analysis of the peristaltic frequency slowing fluctuation interval was carried out to obtain the peristaltic frequency slowing correlation data. The difference in silkworm vitality loss between different growth stages was calculated based on the correlation data of peristalsis frequency slowing down, and the difference in silkworm vitality loss data was obtained.

4. The intelligent environment control method for silkworm breeding according to claim 1, characterized in that: Step S31 includes the following steps: Step S311: analyzing abnormal temperature fluctuations in aggregation behavior during silkworm rearing based on the aggregation behavior-environment interaction effect data to obtain abnormal temperature fluctuation data in aggregation behavior; Step S312: evaluating the temperature fluctuation tolerance of silkworms at different growth stages based on the abnormal temperature fluctuation data of the aggregation behavior and the difference data of the silkworms' environmental requirements, to obtain the temperature fluctuation tolerance data of the silkworms; Step S313: simulating the air circulation of the aggregation behavior during the silkworm breeding process according to the aggregation behavior-environment interaction effect data to obtain aggregation behavior air circulation data; Step S314: analyzing the air duct barrier effect of the clustering behavior during the silkworm breeding process on the clustering behavior air circulation data to obtain the clustering behavior air duct barrier effect data; Step S315: performing demand difference data pairing on the silkworm environmental demand difference data according to the silkworm temperature fluctuation tolerance data and the gathering behavior air duct barrier effect data to obtain environmental demand difference paired data; Step S316: performing behavior activity environment demand regulation based on the paired data according to the environmental demand difference, and obtaining behavior activity environment demand regulation data; wherein the behavior activity environment demand regulation data includes behavior activity temperature regulation data and behavior activity airflow regulation data.

5. The intelligent environment control method for silkworm breeding according to claim 1, characterized in that: Step S34 includes the following steps: Step S341: performing an environmental impact time lag effect analysis on the adjacent activity areas of the silkworm breeding aggregation behavior based on the azimuth distribution environmental impact degree data to obtain distribution environmental impact time lag effect data; Step S342: extracting the environmental temperature mutation and analyzing the airflow structure of the area adjacent to the silkworm breeding gathering behavior based on the temperature control data of the behavior activity, the airflow control data of the behavior activity, and the time lag effect data of the distribution environment, to obtain the azimuthally distributed environmental temperature mutation data and the azimuthally distributed airflow structure data; Step S343: identifying the spatial distribution mutation and progressive law of the adjacent activity areas of the silkworm breeding and aggregation behavior based on the azimuth distribution environmental temperature mutation data to obtain temperature distribution mutation and progressive law data; Step S344: performing intelligent control optimization of the global temperature balance of silkworm rearing based on the temperature distribution mutation and progressive law data and the behavior and activity environment demand control data to obtain temperature balance intelligent control optimization data; Step S345: performing an airflow stacking effect analysis on the azimuthally distributed airflow flow structure data for the adjacent activity areas of the silkworm breeding aggregation behavior to obtain azimuthally distributed airflow stacking effect data; Step S346: performing intelligent control optimization of the global balance of airflow for silkworm breeding based on the azimuth distribution airflow stacking effect data and the behavioral activity environment demand control data to obtain airflow balance intelligent control optimization data; Step S347: performing global balance intelligent control optimization of the silkworm breeding environment according to the temperature balance intelligent control optimization data and the airflow balance intelligent control optimization data to obtain environmental intelligent control optimization data.

6. The intelligent environment control method for silkworm breeding according to claim 5, characterized in that: The intelligent control optimization of airflow global balance based on the azimuth distribution airflow stacking effect data and the behavior activity environment demand control data includes the following steps: The airflow backflow path simulation of the adjacent activity area of ​​mulberry silkworm feeding aggregation behavior was carried out on the azimuthally distributed airflow stacking effect data to obtain the airflow backflow path simulation data; The difficulty of airflow exchange and diffusion is evaluated based on the azimuthal distribution airflow stacking effect data based on the airflow return path simulation data to obtain the airflow exchange and diffusion difficulty data; Optimize the airflow direction angle control based on the airflow exchange and diffusion difficulty data to obtain airflow direction angle control data; Adapting the airflow velocity control to the airflow exchange and diffusion difficulty data according to the airflow direction angle control data to obtain airflow velocity control adaptation data; Based on the airflow direction angle control data, airflow velocity control adaptation data and behavioral activity environment demand regulation data, the global airflow balance intelligent control optimization of silkworm breeding is carried out to obtain the airflow balance intelligent control optimization data.

7. An intelligent environmental control system for silkworm breeding, characterized in that: The intelligent environment control method for silkworm breeding according to claim 1 is used to execute the intelligent environment control method for silkworm breeding, and the intelligent environment control system for silkworm breeding comprises: The silkworm growth stage classification module is used to obtain the silkworm growth cycle data; perform real-time monitoring of the silkworm breeding community to obtain a set of silkworm breeding community monitoring images; classify the silkworm breeding community monitoring image set according to the silkworm growth cycle data to obtain the silkworm growth stage data; The silkworm aggregation behavior environment analysis module is used to analyze the environmental demand differences between different silkworms based on the data of silkworm growth stages, and obtain the silkworm environmental demand difference data; identify the silkworm aggregation behavior based on the silkworm breeding community monitoring image set, and obtain the silkworm aggregation behavior data; and evaluate the aggregation behavior environment interaction effect between different silkworm growth stages based on the silkworm environmental demand difference data, and obtain the aggregation behavior environment interaction effect data; The global control optimization module for silkworm rearing is used to regulate the environmental demand of silkworms' behavior activities based on the aggregated behavior-environment interaction effect data, and obtain the behavior-environment demand regulation data; and to optimize the global balance of the silkworm rearing environment intelligent control based on the behavior-environment demand regulation data, and obtain the environmental intelligent control optimization data; The control management strategy execution module is used to design an automated mulberry silkworm breeding environment control management strategy based on the environmental intelligent control optimization data, obtain the mulberry silkworm breeding environment control management strategy, and send the mulberry silkworm breeding environment control management strategy to the cloud platform to execute the mulberry silkworm breeding intelligent environment control.

Images